Search

In this paper, a novel optimal adaptive radial basis function neural network (RBFNN) control has been investigated for a class of multiple-input-multiple-output (MIMO) nonlinear robot manipulators with uncertain dynamics in discrete time. To facilitate digital implementations of the robot controller, a robot model in discrete time has been employed. A high order uncertain robot model is able to be transformed to a predictor form, and a feedback control system has been then developed without noncausal problem in discrete time. The controller has been designed by an adaptive neural network (NN) based on the feedback system. The adaptive RBFNN robot control system has been investigated by a critic RBFNN and an actor RBFNN to approximate a desired control and a strategic utility function, respectively. The rigorous Lyapunov analysis is used to establish uniformly ultimate boundedness (UUB) of closed-loop signals, and the high-quality dynamic performance against uncertainties and disturbances is obtained by appropriately selecting the controller parameters. Simulation studies validate that the proposed control scheme has performed better than other available methods currently, for robot manipulators. [ABSTRACT FROM AUTHOR]

The present modern power system is getting more complex and dynamic day by day. These Dynamic changes can be effectively handled by integrating renewable sources to the grid. The optimal usage of renewable sources will improve the overall performance of the electrical utility. Renewable energy sources and non-linear loads connected to grid have adverse effects on the power quality of the system. This paper presents I cosine ANFIS control based Dynamic Active Power Filter (DAPF) to improve the power quality of the grid at source side with effective integration of renewable sources. The model presents optimal usage of renewable sources and avoids the usage of battery by replacing with solar energy unit (SEU). DAPF fed by SEU and wind unit serves power to the load during power fluctuations from grid side. The performance of proposed model with I cosine ANFIS controller based DAPF is validated using MATLAB/SIMULINK. [ABSTRACT FROM AUTHOR]

Cogeneration is the simultaneous generation of electricity and useful heat with the aim of exploiting more efficiently the energy stored in the fuel. Cogeneration is, however, a complex process that encompasses a great amount of sub-systems and variables. This fact makes it very difficult to obtain an analytical model of the whole plant, and therefore providing a mechanism or a methodology able to optimize the global behavior. This paper proposes a neuro-genetic strategy for modeling and optimizing a cogeneration process of a real industrial plant. Firstly, the modeling of the process is carried out by means of several interconnected neural networks where, each neural network deals with a particular sub-system of the plant. Next, the obtained models are used by a genetic algorithm, which solves a multiobjective optimization problem of the plant, where the goal is to minimize the fuel consumption and maximize both the generated electricity and the use of the heat. The proposed approach is evaluated with data of a real cogeneration plant collected over a one-year period. Obtained results show not only that the modeling of the plant is correct but also that the optimization increases significantly the efficiency of the cogeneration plant. [ABSTRACT FROM AUTHOR]

Research involving artificial neural networks has tended to be driven towards efficient computation, especially in the domain of pattern recognition, or towards elucidating biological processes in the brain. Models have become more detailed as our understanding of the biology of the brain has increased, incorporating real-time behaviour of individual neurons interacting within complex system structures and dynamics. There are few examples of abstract and fully formal models of biologically plausible neural networks: in the neural networks literature models are often presented as a mixture of mathematical equations and natural language, supported by simulation code and associated experimental results. The informality often hides or obscures important aspects of a particular model, and leaves a large conceptual gap between the model descriptions and the usually low-level programming code used to simulate them. The main contribution of this paper is formally modelling and analysing a biologically plausible neural network model from the literature that exhibits complex neuron-level behaviour and network-level structure. To achieve this a modelling language ‘Pann’ is developed, based on the process algebras CSP and Hybrid χ . It is designed to be convenient for mixing the behaviour of discrete events (such as a neuron spike) with mutable continuous and discrete variables (representing chemical properties of a neuron, for instance). Its behaviour is defined using an operational semantics, from which a set of general properties of the language is proved. The groundwork for the biological model is laid by first formalising some well-known concepts from the artificial neural networks domain, such as feedforward behaviour, backpropagation, and recurrent neural networks. The Pann model of a feedforward network, comprising a set of communicating processes representing individual neurons, is proved equivalent to the standard one-line calculation of feedforward behaviour. [ABSTRACT FROM AUTHOR]

This paper presents a hybrid neural network approach to model magnetic hysteresis at macro-magnetic scale. That approach aims to be coupled together with numerical treatments of magnetic hysteresis such as FEM numerical solvers of the Maxwell's equations in time domain, as in case of the non-linear dynamic analysis of electrical machines, and other similar devices, allowing a complete computer simulation with acceptable run times. The proposed Hybrid Neural System consists of four inputs representing the magnetic induction and magnetic field components at each time step and it is trained by 2D and scalar measurements performed on the magnetic material to be modeled. The magnetic induction B is assumed as entry point and the output of the Hybrid Neural System returns the predicted value of the field H at the same time step. Within the Hybrid Neural System, a suitably trained neural network is used for predicting the hysteretic behavior of the material to be modeled. Validations with experimental tests and simulations for symmetric, non-symmetric and minor loops are presented. [ABSTRACT FROM AUTHOR]

Cluster synchronization is a typical collective behavior in coupled dynamical systems, where the synchronization occurs within one group, while there is no synchronization among different groups. In this paper, under event-based mechanism, pinning cluster synchronization in an array of coupled neural networks is studied. A new event-triggered sampled-data transmission strategy, where only local and event-triggering states are utilized to update the broadcasting state of each agent, is proposed to realize cluster synchronization of the coupled neural networks. Furthermore, a self-triggered pinning cluster synchronization algorithm is proposed, and a set of iterative procedures is given to compute the event-triggered time instants. Hence, this will reduce the computational load significantly. Finally, an example is given to demonstrate the effectiveness of the theoretical results. [ABSTRACT FROM AUTHOR]

Although artificial neural networks have recently gained importance in time series applications, some methodological shortcomings still continue to exist. One of these shortcomings is the selection of the final neural network model to be used to evaluate its performance in test set among many neural networks. The general way to overcome this problem is to divide data sets into training, validation, and test sets and also to select a neural network model that provides the smallest error value in the validation set. However, it is likely that the selected neural network model would be overfitting the validation data. This paper proposes a new model selection strategy (IHTS) for forecasting with neural networks. The proposed selection strategy first determines the numbers of input and hidden units, and then, selects a neural network model from various trials caused by different initial weights by considering validation and training performances of each neural network model. It is observed that the proposed selection strategy improves the performance of the neural networks statistically as compared with the classic model selection method in the simulated and real data sets. Also, it exhibits some robustness against the size of the validation data. [ABSTRACT FROM AUTHOR]

Spoken dialog systems have been proposed as a solution to facilitate a more natural human–machine interaction. In this paper, we propose a framework to model the user׳s intention during the dialog and adapt the dialog model dynamically to the user needs and preferences, thus developing more efficient, adapted, and usable spoken dialog systems. Our framework employs statistical models based on neural networks that take into account the history of the dialog up to the current dialog state in order to predict the user׳s intention and the next system response. We describe our proposal and detail its application in the Let׳s Go spoken dialog system. [ABSTRACT FROM AUTHOR]

In this article, we present a data-free method to solve differential equation using artificial neural networks (ANN). This method exploits the universal function approximation nature of a neural network to mimic a specified partial differential equation (PDE) and provide its solution. Specifically, use of simple feed-forward artificial neural network (FF-ANN) is shown to demonstrate the solution of 1-D second-order differential equations without use of any prior data. The article also demonstrates that the similarity in two PDEs is akin to similarity in the optimized weight matrices attained after the solution using FF-ANN. This property is then utilized for a transferred learning to enable faster convergence of a new PDE, based on the prior solution of a similar PDE. The concept is shown while considering a general form of second-order PDE, and considering specific cases of scalar in-homogeneous wave equation form and Poisson Equation form. Error convergence below 10−6 is shown and the transferred learning process shows typical time acceleration by a factor of 1.5–3 for the considered equations. [ABSTRACT FROM AUTHOR]

Data based modeling applications require the complete automation of model creation of, in general, nonlinear processes. Numerous model architectures are available to approximate complex data structures, however, creating and selecting the best model provides a present challenge for application. Model ensembles provide excellent strategies if the prediction performance of the models can be assessed in some way. Information criteria approaches, trading off goodness of fit criteria against the average variance error of the model structures, are theoretically applicable, but demonstratively perform poorly in settings with sparse data sets and complex model structures, settings which are present for many industrial purposes. This paper proposes and discusses a methodology how to regularise the weight calculation building model ensembles. Thereby, the weights trade off goodness of fit criteria against empirical measures of risk, increasing the model ensemble prediction performance. The methodology is independent of the model class, applicable to all black box models, and improves prediction performance for a variety of data in several industrial application areas. [ABSTRACT FROM AUTHOR]

This paper proposes an algorithm for creating rules of a fuzzy logic system using a neuro-fuzzy approach. The proposal is based on the results of Juang and Tsao who use a Fuzzy Neural Network (FNN) to generate rules and fuzzy sets from input data. A time series example is solved using our proposal, which is tested using statistical analysis of the residuals of the model. [ABSTRACT FROM AUTHOR]

Machine learning is a very important approach to pattern classification. This paper provides a better insight into Incremental Attribute Learning (IAL) with further analysis as to why it can exhibit better performance than conventional batch training. IAL is a novel supervised machine learning strategy, which gradually trains features in one or more chunks. Previous research showed that IAL can obtain lower classification error rates than a conventional batch training approach. Yet the reason for that is still not very clear. In this study, the feasibility of IAL is verified by mathematical approaches. Moreover, experimental results derived by IAL neural networks on benchmarks also confirm the mathematical validation. [ABSTRACT FROM AUTHOR]

Object grasping by robot hands is challenging due to the hand and object modeling uncertainties, unknown contact type and object stiffness properties. To overcome these challenges, the essential purpose is to achieve the mathematical model of the robot hand, model the object and the contact between the object and the hand. In this paper, an intelligent hand-object contact model is developed for a coupled system assuming that the object properties are known. The control is simulated in the Matlab Simulink/SimMechanics, Neural Network Toolbox and Computer Vision System Toolbox. [ABSTRACT FROM AUTHOR]

Scale is highly detrimental to surface quality for tinplate products. There are a large number of process variables at a typical hot mill and principal component analysis is a well-known technique for reducing the number of process variables. This paper estimates the principal components associated with the hot mill process variables and puts these through an Adaptive Neuro Fuzzy Inference System (ANFIS) to find those hot mill running conditions that will minimise the amount of scale observed on the bottom of the rolled strip. It was found that the variation observed in all the hot mill process variables could be captured through the use of just six principal components, and that using just three of these in an ANFIS was sufficient to identify those operating conditions leading to coils being produced with a consistently low scale count. Specifically, it was found that the best operating conditions for the hot mill were when the first component was lower than -0.098 the second lower than 0.8058 and the third higher than -0.482. These ranges in turn corresponded to certain hot mill temperatures that depended to some extent on the base chemistry of the incoming slab. [ABSTRACT FROM AUTHOR]

Originally inspired by biological neural networks, artificial neural networks (ANNs) are powerful mathematical tools that can solve complex nonlinear problems such as filtering, classification, prediction and more. This paper demonstrates the first successful implementation of ANN, specifically nonlinear autoregressive with exogenous input (NARX) networks, to estimate the hemodynamic states and neural activity from simulated and measured real blood oxygenation level dependent (BOLD) signals. Blocked and event-related BOLD data are used to test the algorithm on real experiments. The proposed method is accurate and robust even in the presence of signal noise and it does not depend on sampling interval. Moreover, the structure of the NARX networks is optimized to yield the best estimate with minimal network architecture. The results of the estimated neural activity are also discussed in terms of their potential use. [ABSTRACT FROM AUTHOR]

Abstract: Achieving a low Noise-to-Signal Ratio (NSR) is one of the major concerns when implementing hardware-based neural networks. Continuous Valued Number System (CVNS) features have been exploited to improve the NSR. The efficiency of the network model in terms of area, power consumption, and NSR is measured using the product of the total number of neurons in the network multiplied by the network NSR, which indicates the number of neurons required for a specific NSR. The network proposed in this paper stores the weights in digital registers while the processing is done in the analog domain using CVNS arithmetic. The mathematical analysis and comparison between the proposed network and the previous structures prove that the proposed architecture improves upon in terms of both the NSR and the product of neuron multiplied by NSR. [Copyright &y& Elsevier]

This paper presents a new approach for incorporating the thermal effect on the magnetic hysteresis of the 3F3 material. The proposed algorithm is based on the knowledge of the magnetic flux density spectrum for some temperatures. So, a feed-forward neural network is trained to learn the relation between the rank of harmonics, the temperature and the amplitude of each harmonic. To construct the hysteresis loop for a new value of the temperature, the neural network predicts the spectrum of the magnetic flux density B which is transformed back to the time domain. [ABSTRACT FROM AUTHOR]

The fault detection of industrial processes is very important for increasing the safety, reliability and availability of the different components involved in the production scheme. In this paper, a fault detection (FD) method is developed for nonlinear systems. The main contribution consists in the design of this FD scheme through a combination of the Bayes theorem and a neural adaptive black-box identification for such systems. The performance of the proposed fault detection system has been tested on a real plant as a distillation column. The simplicity of the developed neural model of normal condition operation, under all regimes (i.e. steady-state and unsteady state), used in this case is realised by means of a NARX (Nonlinear Auto-Regressive with exogenous input) model and by an experimental design. To show the effectiveness of proposed fault detection method, it was tested on a realistic fault of a distillation plant of laboratory scale. [ABSTRACT FROM AUTHOR]

The stability of stopes in underground mines is an active research area worldwide. Stope failures are the main cause of fatal accidents in the mining industry and the intensity of failures is likely to increase as the scale of underground mining activity increases. This work investigates stope stability using four multidisciplinary random variables. The stope stability function is approximated by training feed forward neural networks with a genetic algorithm and resilient back propagation. The proposed method is used to approximate the stope stability function of three existing bauxite stopes and is compared to results obtained from the empirical stability graph method, the voussoir beam analogue and discontinuous deformation analysis. The neural network model is shown to be superior to the other methods, as, unlike the conventional approaches, it predicts the failure or the likelihood of stope instabilities. [ABSTRACT FROM AUTHOR]

In this paper we devise a neural-network-based model to improve the production workflow of organic solar cells (OSCs). The investigated neural model is used to reckon the relation between the OSC's generated power and several device's properties such as the geometrical parameters and the active layers thicknesses. Such measurements were collected during an experimental campaign conducted on 80 devices. The collected data suggest that the maximum generated power depends on the active layer thickness. The mathematical model of such a relation has been determined by using a feedforward neural network (FFNN) architecture as a universal function approximator. The performed simulations show good agreement between simulated and experimental data with an overall error of about 9%. The obtained results demonstrate that the use of a neural model can be useful to improve the OSC manufacturing processes. [ABSTRACT FROM AUTHOR]

Abstract: Inferential sensing, or soft sensing, gained popularity in recent years as an alternative to continuous emission monitoring systems because of its simplicity, reliability, and cost effectiveness as compared to analogous hardware sensors. In this paper we address the problem of NO x emission using a model of furnace of an industrial boiler, and propose a neural network structure for high performance prediction of NO x as well as O2. The studied boiler is 160MW, gas fired with natural gas, water-tube boiler, having two vertically aligned burners. The boiler model is a 3D problem that involves turbulence, combustion, radiation in addition to NO x modeling. The 3D computational fluid dynamic model is developed using Fluent simulation package. The model provides calculations of the 3D temperature distribution as well as the rate of formation of the NO x pollutant, enabling a better understanding on how and where NO x are produced. The boiler was simulated under various operating conditions. The generated data is then used for initial development and assessment of neural network soft sensors for emission prediction based on the conventional process variable measurements. The performance of the proposed soft sensor is then evaluated using actual data from an industrial boiler. The developed soft sensor achieves comparable accuracy to the continuous emission monitor analyzer, however, with substantial reduction in the cost of equipment and maintenance. [Copyright &y& Elsevier]

Abstract: In this paper, together with some Lyapunov–Krasovskii functionals and effective mathematical techniques, several conditions are derived to guarantee a class of neural networks with discrete and distributed time-varying delays to be globally exponential stability. Finally, two numerical examples are given to illustrate the effectiveness of the proposed methods. [Copyright &y& Elsevier]

Mistuning affects forced response of bladed disks drastically; therefore, its identification plays an essential role in the forced response analysis of bladed disk assemblies. Forced response analysis of mistuned bladed disk assemblies has drawn wide attention of researchers but there are a very limited number of studies dealing with identification of mistuning, especially if the component under consideration is an integrally bladed disk (blisk). This paper presents two new methods to identify mistuning of a bladed disk from the assembly modes via utilizing cascaded optimization and neural networks. It is assumed that a tuned mathematical model of the blisk under consideration is readily available, which is always the case for today's realistic bladed disk assemblies. In the first method, a data set of selected mode shapes and natural frequencies is created by a number of simulations performed by mistuning the tuned mathematical model randomly. A neural network created by considering the number of modes, is then trained with this data set. Upon training the network, it is used to identify mistuning of the rotor from measured data. The second method further improves the first one by using it as a starting point of an optimization routine and carries out an optimization to identify mistuning. To carry out identification analysis by means of the proposed methods, there are no limitations on the number of modes or natural frequencies to be used. Thus, unlike existing mistuning identification methods they are suitable for incomplete data as well. Moreover, since system modes are used rather than blade alone counterparts, the techniques are ready to be used for analysis of blisks. Case studies are performed to demonstrate the capabilities of the new methods by using two different mathematical models to create training data sets a lumped-parameter model and a relatively realistic reduced order model. Throughout the case studies, the effects of using incomplete mode families and random errors in assembly modes are investigated. The results show that, the proposed method utilizing cascaded optimization and neural networks can identify mistuning parameters of a realistic blisk system with an exceptional accuracy even in the presence of incomplete and noisy test data. [ABSTRACT FROM AUTHOR]

Abstract: The use of mathematical tools such as Artificial Neural Networks and Fuzzy Logic has been shown to be useful for solving complex engineering problems, without the need to reproduce the phenomenon under study, when the only information available consists of the parameters of the problem and the desired results. Based on a collection of 96 laboratory tests, this paper uses Artificial Neural Networks and Fuzzy Logic to determine the compressive strength of a masonry structure composed of clay bricks and cement mortar, by using only two parameters: the compressive strength of the mortar and that of the bricks. These mathematical techniques are an alternative to the complex analytical formulas dependent on a large number of parameters and to empirical formulas, which, even though simple, often give unrealistic values. The results obtained are compared to the calculation methods proposed by other authors and other standards and demonstrate the suitability of using Neural Networks and Fuzzy Logic to predict the compressive strength of masonry. [Copyright &y& Elsevier]

Abstract: This paper uses an artificial neural network (ANN) and Levenberg–Marquardt training algorithm to model the nonlinear relationship between refractive index and energy gap in semiconductors. The predicted simulation values of the ANN are in accordance with the experimental data. An error deviation (Δn) was estimated for different models. The lowest deviation is given by the ANN model. The ANN model performance was also tested for some compounds not included in the training and was found to be in good agreement with the experimental data. High precision of the NN model is demonstrated as well as good generalization performance. [Copyright &y& Elsevier]

Abstract: In this paper we consider a simple discrete Hopfield neural network model and analyze local stability using the associated characteristic model. In order to study the dynamic behavior of the quasi-periodic orbit, the Hopf bifurcation must be determined. For the case of two neurons, we find one necessary condition that yields the Hopf bifurcation. In addition, we determine the stability and direction of the Hopf bifurcation by applying normal form theory and the center manifold theorem. An example is given and a numerical simulation is performed to illustrate the results. We analyze the influence of bias weights on the stability of the quasi-periodic orbit and study the phase-locking phenomena for certain experimental results with Arnold Tongues in a particular weight configuration. [Copyright &y& Elsevier]

Abstract: Supplier selection and evaluation is a complicated and disputed issue in supply chain network management, by virtue of the variety of intellectual property of the suppliers, the several variables involved in supply demand relationship, the complex interactions and the inadequate information of suppliers. The recent literature confirms that neural networks achieve better performance than conventional methods in this area. Hence, in this paper, an effective artificial intelligence (AI) approach is presented to improve the decision making for a supply chain which is successfully utilized for long-term prediction of the performance data in cosmetics industry. A computationally efficient model known as locally linear neuro-fuzzy (LLNF) is introduced to predict the performance rating of suppliers. The proposed model is trained by a locally linear model tree (LOLIMOT) learning algorithm. To demonstrate the performance of the proposed model, three intelligent techniques, multi-layer perceptron (MLP) neural network, radial basis function (RBF) neural network and least square-support vector machine (LS-SVM) are considered. Their results are compared by using an available dataset in cosmetics industry. The computational results show that the presented model performs better than three foregoing techniques. [Copyright &y& Elsevier]

Abstract: Shortest path tree (SPT) computation is a critical issue in many real world problems, such as routing in networks. It is also a constrained optimization problem, which has been studied by many authors in recent years. Typically, it is solved by heuristic algorithms, such as the famous Dijkstra''s algorithm, which can quickly provide a good solution in most instances. However, with the scale of problem increasing, these methods are inefficient and may consume a considerable amount of CPU time. Neural networks, which are massively parallel models, can solve this question easily. This paper presents an efficient modified continued pulse coupled neural network (MCPCNN) model for SPT computation in a large scale instance. The proposed model is topologically organized with only local lateral connections among neurons. The start neuron fires first, and then the firing event spreads out through the lateral connections among the neurons, like the propagation of a wave. Each neuron records its parent, that is, the neighbor which caused it to fire. It proves that the generated wave in the network spreads outward with travel times proportional to the connection weight between neurons. Thus, the generated path is always the global optimal shortest path from the source to all destinations. The proposed model is also applied to generate SPTs for a real given graph step by step. The effectiveness and efficiency of the proposed approach is demonstrated through simulation and comparison studies. [Copyright &y& Elsevier]

Abstract: Neural network systems are highly capable of deriving knowledge from complex data, and they are used to extract patterns and trends which are otherwise hidden in many applications. Preserving the privacy of sensitive data and individuals'' information is a major challenge in many of these applications. One of the most popular algorithms in neural network learning systems is the back-propagation (BP) algorithm, which is designed for single-layer and multi-layer models and can be applied to continuous data and differentiable activation functions. Another recently introduced learning technique is the extreme learning machine (ELM) algorithm. Although it works only on single-layer models, ELM can out-perform the BP algorithm by reducing the communication required between parties in the learning phase. In this paper, we present new privacy-preserving protocols for both the BP and ELM algorithms when data is horizontally and vertically partitioned among several parties. These new protocols, which preserve the privacy of both the input data and the constructed learning model, can be applied to online incoming records and/or batch learning. Furthermore, the final model is securely shared among all parties, who can use it jointly to predict the corresponding output for their target data. [Copyright &y& Elsevier]

Abstract: This paper investigates the development and experimental implementation of an adaptive dynamic nonlinear model inversion control law for a Twin Rotor MIMO System (TRMS) using artificial neural networks. The TRMS is a highly nonlinear aerodynamic test rig with complex cross-coupled dynamics and therefore represents the control challenges of modern air vehicles. A highly nonlinear 1DOF mathematical model of the TRMS is considered in this study and a nonlinear inverse model is developed for the pitch channel of the system. An adaptive neural network element is integrated thereafter with the feedback control system to compensate for model inversion errors. The proposed on-line learning algorithm updates the weights and biases of the neural network using the error between the set-point and the real output. The real-time response of the method shows a satisfactory tracking performance in the presence of inversion errors caused by model uncertainty. The approach is therefore deemed to be suitable to apply real-time to other nonlinear systems with necessary modifications. [Copyright &y& Elsevier]

Abstract: This paper presents a rule-based approach for the classification of power quality disturbances. The disturbed signal is first characterized using the multi-resolution S-transform, which acts as a feature extraction tool. Then, a simple but robust rule-based classification algorithm is used to identify disturbances. This algorithm uses linear and parabolic rules as pattern classifiers where decision boundaries are established by a heuristic search. The classification algorithm has a modular structure where each module works separately to detect specific disturbances. The most common types of disturbances, including sags, interruptions, swells, harmonics and oscillatory transients, were analyzed. Moreover, complex disturbances consisting of combinations of two simple events (simultaneous or consecutive in the same interval) were also analyzed. In both cases, noise, ranging from 40 to 20dB, was also considered. The tested data set contains power quality signals obtained using mathematical models, power quality events obtained from power network''s simulations using PSCAD/EMTDC and measured signals at electrical installations. Finally, evaluation results verifying the accuracy of the proposed method are presented and compared to those obtained from a classification system based on an artificial neural network. [Copyright &y& Elsevier]

Abstract: Dynamic pricing is a pricing strategy where price for the product changes according to the expected demand for it. Some work on using neural network for dynamic pricing have been previously reported, such as for forecasting the demand and modelling consumer choices. However, little work has been done in using them for optimising pricing policies. In this paper, we describe how neural networks and evolutionary algorithms can be combined together to optimise pricing policies. Particularly, we build a neural network based demand model and use evolutionary algorithms to optimise policy over build model. There are two key benefits of this approach. Use of neural network makes it flexible enough to model a range of different demand scenarios occurring within different products and services, and the use of evolutionary algorithm makes it versatile enough to solve very complex models. We also evaluate the pricing policies found by neural network based model to that found by other widely used demand models. Our results show that proposed model is more consistent, adapts well in a range of different scenarios, and in general, finds more accurate pricing policy than other three compared models. [Copyright &y& Elsevier]

Summary: Estimation of suspended sediment concentration carried by a river is very important for many water resources projects. The accuracy of artificial neural networks (ANN) with artificial bee colony (ABC) algorithm is investigated in this paper for modeling discharge-suspended sediment relationship. The ANN–ABC was compared with those of the neural differential evolution, adaptive neuro-fuzzy, neural networks and rating curve models. The daily stream flow and suspended sediment concentration data from two stations, Rio Valenciano Station and Quebrada Blanca Station, were used as case studies. For evaluating the ability of the models, mean square error and determination coefficient criteria were used. Comparison results showed that the ANN–ABC was able to produce better results than the neural differential evolution, neuro-fuzzy, neural networks and rating curve models. The logarithm transformed data were also used as input to the proposed ANN–ABC models. It was found that the logarithm transform significantly increased accuracy of the models in suspended sediment estimation. [ABSTRACT FROM AUTHOR]

Abstract: This paper proposes a novel, model-based control strategy for absorption cooling systems. First, a small-scale absorption chiller was modelled using artificial neural networks (ANNs). This model takes into account inlet and outlet temperatures as well as the flow rates of the external water circuits. The configuration 9–6–2 (9 inputs, 6 hidden and 2 output neurons) showed excellent agreement between the prediction and the experimental data (R 2 >0.99 and RMSE<0.05%). This type of ANN model is used to explain the behaviour of the system when operating conditions are measured and these measurements are available. A control strategy was also developed by using the inverse artificial neural network (ANNi) method. For a particular output (cooling load) the ANNi calculates the optimal unknown parameter(s) (controlling temperatures and flow rates). An optimization method was used to fit the unknown parameters of the ANNi method. The very low percentage of error and short computing time make this methodology suitable for the on-line control of absorption cooling systems. [Copyright &y& Elsevier]

Abstract: The search capabilities of the Differential Evolution (DE) algorithm – a global optimization technique – make it suitable for finding both the architecture and the best internal parameters of a neural network, usually determined by the training phase. In this paper, two variants of the DE algorithm (classical DE and self-adaptive mechanism) were used to obtain the best neural networks in two distinct cases: for prediction and classification problems. Oxygen mass transfer in stirred bioreactors is modeled with neural networks developed with the DE algorithm, based on the consideration that the oxygen constitutes one of the decisive factors of cultivated microorganism growth and can play an important role in the scale-up and economy of aerobic biosynthesis systems. The coefficient of mass transfer oxygen is related to the viscosity, superficial speed of air, specific power, and oxygen-vector volumetric fraction (being predicted as function of these parameters) using stacked neural networks. On the other hand, simple neural networks are designed with DE in order to classify the values of the mass transfer coefficient oxygen into different classes. Satisfactory results are obtained in both cases, proving that the neural network based modeling is an appropriate technique and the DE algorithm is able to lead to the near-optimal neural network topology. [Copyright &y& Elsevier]

Abstract: Indirect electrolysis has been used for the removal of chlorophyll a (as indicator of algae) from the final effluent of aerated lagoons in the wastewater treatment plant of Bu-Ali Industrial Estate. The efficiency of the process was studied experimentally and by simulation using neural networks. The process analysis was done in different conditions of retention time (5–50min) and using two types of electrodes based on aluminum and stainless steel, with different distances between electrodes (from 1.0 to 3.5cm). The electrical current and the average voltage applied were between 5 and 90A (0.74–12Adm−3) and 50V, respectively. The influence of the main parameters of the electrolysis process on the final values for chlorophyll a, TSS and COD is evaluated experimentally. On the other hand, predictions of the main system outputs of a treated waste as a function of initial characteristics (initial values of chlorophyll a, TSS, COD) and operation conditions (temperature, electric power, time, electrode distance, and electrode type) were performed using artificial neural networks. The modeling methodologies elaborated in this paper are based on different types of neural networks, used individually or aggregated in stacks. They were developed gradually in the sense of improving the model performance. The neural network results represent accurate predictions, useful for experimental practice. [Copyright &y& Elsevier]

Abstract: In the field of transportation, data analysis is probably the most important and widely used research tool available. In the data analysis universe, there are two ‘schools of thought’; the first uses statistics as the tool of choice, while the second – one of the many methods from – Computational Intelligence. Although the goal of both approaches is the same, the two have kept each other at arm’s length. Researchers frequently fail to communicate and even understand each other’s work. In this paper, we discuss differences and similarities between these two approaches, we review relevant literature and attempt to provide a set of insights for selecting the appropriate approach. [Copyright &y& Elsevier]

The main purpose of this paper is to give a mathematical description of flow stress of examined aluminium alloys on the basis of upsetting tests performed in a servohydraulic plastometer. Deformation curves have been described by means of the Sellars-Tegart-Garofalo equation, with the aid of linear regression analysis and by the neural network method implemented in the NEUREX program. [ABSTRACT FROM AUTHOR]

Abstract: This paper proposes a new intelligence paradigm scheme to forecast that emphasizes on numerous software development elements based on functional networks forecasting framework. The most common methods for estimating software development efforts that have been proposed in literature are: line of code (LOC)-based constructive cost model (COCOMO), function point (FP) based on neural networks, regression, and case-based reasoning (CBR). Unfortunately, such forecasting models have numerous of drawbacks, namely, their inability to deal with uncertainties and imprecision present in software projects early in the development life-cycle. The main benefit of this study is to utilize both function points and development environments of recent software development cases prominent, which have high impact on the success of software development projects. Both implementation and learning process are briefly proposed. We investigate the efficiency of the new framework for predicting the software development efforts using both simulation and COCOMO real-life databases. Prediction accuracy of the functional networks framework is evaluated and compared with the commonly used regression and neural networks-based models. The results show that the new intelligence paradigm predicts the required efforts of the initial stage of software development with reliable performance and outperforms both regression and neural networks-based models. [ABSTRACT FROM AUTHOR]

Abstract: The Spinning Enhanced Visible and Infrared Imager (SEVIRI) measurements from the Meteosat Second Generation (MSG) satellites enable global monitoring of the distribution of clouds during day and night, with a spatial, temporal and spectral resolution that allows for better understanding of the role of clouds in global radiation budget and in climate in general. A method to retrieve cloud properties from nighttime SEVIRI measurements is described in this paper. The method is applicable to single-layer water clouds over sea surfaces and it is based on the inversion of a forward theoretical radiative transfer model, that simulates the radiances reaching the SEVIRI infrared detectors from a specified configuration of the earth–cloud–atmosphere system. This model accounts for scattering and absorption processes in the assumed horizontally homogeneous adiabatic cloud layer. For the inversion of this model, artificial neural networks techniques have been used in this work. The main advantage that these techniques provide is their low computational cost, which makes them suitable for the implementation of operational retrieval procedures. Results obtained by the proposed method are compared with the values provided by the CloudSat derived 2B-TAU product, and those derived from NOAA-AVHRR nighttime imagery, obtaining good agreements. [ABSTRACT FROM AUTHOR]

Abstract: This paper discusses a computationally efficient approach to set-point optimisation which cooperates with predictive control and its application to a multivariable neutralisation reactor. In the presented system structure a neural Hammerstein model of the process is used. For set-point optimisation, a linearisation of the steady-state model derived from the neural Hammerstein model is calculated on-line. As a result, the set-point is determined from a linear programming problem. For predictive control, a linear approximation of the neural Hammerstein model is calculated on-line and the control policy is determined from a quadratic programming problem. Thanks to linearisation, the necessity of on-line nonlinear optimisation is eliminated. This article emphasises advantages of neural Hammerstein models: accuracy, a limited number of parameters and a simple structure. Thanks to using such models, model transformations can be carried out very efficiently on-line. It is demonstrated that results obtained in the presented structure are very close to those achieved in a computationally demanding structure with on-line nonlinear optimisation. It is also shown that for the considered neutralisation reactor the classical system structure in which for control and set-point optimisation linear models are used gives numerically wrong results. [Copyright &y& Elsevier]

Abstract: This paper presents an application which uses Feedforward Neural Networks (FNNs) to model the nonlinear behaviour of the drying of seedy grapes. First, a novel type of dryer for experimentally and mathematically evaluating the thin-layer drying kinetics of seedy grapes is developed. In the developed drying system, an expanded-surface solar air collector, a solar air collector with Phase-Change Material (PCM) and drying room with swirl element have been particularly included. Secondly, the drying rate is estimated as an exponential-type equation using non-linear regression analysis. Thirdly, the drying rate of seedy grapes is estimated using an FNN. Finally, the performance of the FNN model is compared with those of nonlinear and linear regression models by means of the root mean square errors, the mean absolute errors, and the correlation coefficient statistics. The results indicate that the FNN is more accurate and performed more consistently than alternative approaches employed in estimating drying rate. [ABSTRACT FROM AUTHOR]

Abstract: The purpose of the paper was to extract important features of children’s mathematical gift by using neural networks and logistic regression, in order to create a model that will assist teachers in elementary schools to recognize mathematically gifted children in an early stage, therefore enabling further development and realization of that gift. The initial model was created on the basis of a theoretical background and heuristical knowledge on giftedness in mathematics, including five components: (1) mathematical competencies, (2) cognitive components of gift, (3) personal components that contribute gift development, (4) environmental factors, and (5) efficiency of active learning and exercising methods, as well as grades and out-of-school activities of pupils in the fourth year of elementary school. The three neural network classification algorithms were tested in order to extract the important variables for detecting mathematically gifted children. The best neural network model was selected on the basis of a 10-fold cross-validation procedure. The model was also investigated by the logistic regression. Important predictors detected by two methods were compared and analyzed. The results show that both methods extract similar set of variables as the most important, including grades in mathematics, mathematical competencies of a child regarding numbers and calculating, but also grades in the literature, and environmental factors. [Copyright &y& Elsevier]

Abstract: A magnetic tube recovery ratio (MTRR) is an important index in mineral processing, though it cannot be measured online. Real-time control for this product index is impossible. In this paper a new soft sensing method is proposed, which uses fuzzy system and neural network techniques. The contributions of our soft sensing method are that a fuzzy mechanism model for MTRR is used, which is obtained from data clustering. We do not update the fuzzy model, but use a neural compensator to improve the modeling accuracy, where the training algorithm for the neural network stable. This soft sensing method has been successfully applied in a metal company in China. [ABSTRACT FROM AUTHOR]

Abstract: Selecting relevant features to make a decision and expressing the relationships between these features is not a simple task. The decision maker must precisely define the alternatives and criteria which are more important for the decision making process. The Analytic Hierarchy Process (AHP) uses hierarchical structures to facilitate this process. The comparison is realized using pairwise matrices, which are filled in according to the decision maker judgments. Subsequently, matrix consistency is tested and priorities are obtained by calculating the matrix principal eigenvector. Given an incomplete pairwise matrix, two procedures must be performed: first, it must be completed with suitable values for the missing entries and, second, the matrix must be improved until a satisfactory level of consistency is reached. Several methods are used to fill in missing entries for incomplete pairwise matrices with correct comparison values. Additionally, once pairwise matrices are complete and if comparison judgments between pairs are not consistent, some methods must be used to improve the matrix consistency and, therefore, to obtain coherent results. In this paper a model based on the Multi-Layer Perceptron (MLP) neural network is presented. Given an AHP pairwise matrix, this model is capable of completing missing values and improving the matrix consistency at the same time. [Copyright &y& Elsevier]

Abstract: In order to improve the prediction rates of churn prediction in land-line telecommunication service field, this paper proposes a new set of features with three new input window techniques. The new features are demographic profiles, account information, grant information, Henley segmentation, aggregated call-details, line information, service orders, bill and payment history. The basic idea of the three input window techniques is to make the position order of some monthly aggregated call-detail features from previous months in the combined feature set for testing be as the same one as for training phase. For evaluating these new features and window techniques, the two most common modelling techniques (decision trees and multilayer perceptron neural networks) and one of the most promising approaches (support vector machines) are selected as predictors. The experimental results show that the new features with the new window techniques are efficient for churn prediction in land-line telecommunication service fields. [Copyright &y& Elsevier]

Abstract: This contribution describes the pattern recognition based data analysis of an existing industrial batch dryer, and the comparison of three artificial intelligence techniques suited to perform classification tasks: neural networks trained using the Levenberg–Marquardt and the Levenberg–Marquardt method with Bayesian regularization, the neuro-fuzzy model based on clustering and grid partition, and the Takagi–Sugeno fuzzy models. The classifiers are used to quantify the dryer batch time and its variation during a certain production period, thus the motivation behind the work is genuine. The presented pattern recognition method implements a supervised learning approach and is based on pressure measurement profiles recorded by the plant data management software—the PI System from OSIsoft. It is found that the neural networks trained with the Bayesian regularization have shown the most robust classification performance with respect to separation threshold selection. Furthermore, it is concluded that the application of artificial intelligence techniques in real chemical manufacturing facilities is feasible and provides useful information for process performance monitoring purposes. The pattern recognition findings presented in this paper are not case specific and can be directly used for the monitoring of a large variety of drying processes since the pressure profile features – vacuum check, pressure decrease, vacuum break – do not depend on the chemicals which are dried. Since the development of the artificial intelligent classifiers is presented in detail and step by step, this work may be interesting as a pattern recognition tutorial for chemical engineers. [Copyright &y& Elsevier]

Abstract: A data-driven approach for maximization of the power produced by wind turbines is presented. The power optimization objective is accomplished by computing optimal control settings of wind turbines using data mining and evolutionary strategy algorithms. Data mining algorithms identify a functional mapping between the power output and controllable and non-controllable variables of a wind turbine. An evolutionary strategy algorithm is applied to determine control settings maximizing the power output of a turbine based on the identified model. Computational studies have demonstrated meaningful opportunities to improve the turbine power output by optimizing blade pitch and yaw angle. It is shown that the pitch angle is an important variable in maximizing energy captured from the wind. Power output can be increased by optimization of the pitch angle. The concepts proposed in this paper are illustrated with industrial wind farm data. [Copyright &y& Elsevier]

Abstract: Previous studies in mechanical and column flotation cells have shown that bubble surface area flux (Sb) is an appropriate indicator of gas dispersion in a flotation cell which has a relatively strong correlation with flotation rate constant. In the present investigation, based on extensive tests conducted in an industrial Metso Minerals CISA flotation column (4m in diameter and 12m in height) in a rougher circuit, Sb as a function of the most significant operating variables which affect gas dispersion in a flotation column (i.e. superficial gas velocity, slurry density (solids%) and frother dosage/type) was modeled using artificial neural network (ANN) and statistical (non-linear regression) techniques. The models were developed taking into consideration a data set consisting of 82 experimental tests conducted in an industrial rougher column (at a copper concentrator in Iran) operating under a variety of experimental conditions. This paper outlines the development of the models and validation using a number of randomly selected datasets. Limitations of the present models are discussed and comments and recommendations on further investigations are given. [Copyright &y& Elsevier]